SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · Li_Deep_Random_Projector_Accelerated_Deep_Image_Prior_CVPR_2023_paper · CVPR · 2023

Deep Random Projector: Accelerated Deep Image Prior

Hengkang Wang, Taihui Li, Ju Sun, Zhong Zhuang

Code that ran

7 of 10 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 3 failures of our instrument; 3 no recorded run), measured 2026-11-21; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/Li_Deep_Random_Projector_Accelerated_Deep_Image_Prior_CVPR_2023_paper.json · badge: /api/ran/Li_Deep_Random_Projector_Accelerated_Deep_Image_Prior_CVPR_2023_paper.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
sun-umn/Deep-Random-Projector canonical (classifier label)
classifier basis: census
7 ran · 3 no recorded run
FunctionStatusWhere it lives
act Ran
ran; our contract draft was wrong, not the code
sun-umn/Deep-Random-Projector/1_Denoising/models/common.py
pointer only (licence: MIT); the stored copy get_code serves, from dniku/perceptual-gradient-networks, is pointer only (licence: MPL-2.0) · get_code("e3edcd371d85dd22")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from dniku/perceptual-gradient-networks, and MPL-2.0, as GitHub detects it on that repository, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

bn Ran
ran; our contract draft was wrong, not the code
sun-umn/Deep-Random-Projector/1_Denoising/models/common.py
pointer only (licence: MIT); the stored copy get_code serves, from dniku/perceptual-gradient-networks, is pointer only (licence: MPL-2.0) · get_code("cd7e7024386fb823")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from dniku/perceptual-gradient-networks, and MPL-2.0, as GitHub detects it on that repository, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

calcualte_PSNR Ran
ran on a synthesized input
sun-umn/Deep-Random-Projector/1_Denoising/psnr_ssim.py
code served (permissive licence) · get_code("6911cf7209ee6f23")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned float64, ndim 0, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np
import torch

torch.manual_seed(0)

# The function expects two image arrays with shape (C, H, W)
# that will be transposed to (H, W, C) for PSNR calculation
# We need small arrays with distinct dimensions for clarity

# Create two small image arrays with shape (C, H, W)
# C=3 (channels), H=4 (height), W=5 (width)
im_true = np.random.randint(0, 256, size=(3, 4, 5), dtype=np.uint8)
im_test = np.random.randint(0, 256, size=(3, 4, 5), dtype=np.uint8)

ARGS = {
    "im_true": im_true,
    "im_test": im_test,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, skimage, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
conv Ran
ran; our contract draft was wrong, not the code
sun-umn/Deep-Random-Projector/1_Denoising/models/common.py
pointer only (licence: MIT); the stored copy get_code serves, from dniku/perceptual-gradient-networks, is pointer only (licence: MPL-2.0) · get_code("040cc21cdcd6aae9")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from dniku/perceptual-gradient-networks, and MPL-2.0, as GitHub detects it on that repository, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

conv Ran
ran on a synthesized input
sun-umn/Deep-Random-Projector/1_Denoising/models/texture_nets.py
code served (permissive licence) · get_code("d52895da7c9b3295")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Conv2d. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    'in_f': 3,
    'out_f': 64,
    'kernel_size': 3,
    'stride': 1,
    'bias': True,
    'pad': 'zero'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
dcgan Ran
ran on a synthesized input
sun-umn/Deep-Random-Projector/1_Denoising/models/dcgan.py
code served (permissive licence) · get_code("e3f6da1942f8bad7")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Sequential. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    'inp': 2,
    'ndf': 32,
    'num_ups': 4,
    'need_sigmoid': True,
    'need_bias': True,
    'pad': 'zero',
    'upsample_mode': 'nearest',
    'need_convT': True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_kernel Ran
ran, honoured the contract we drafted
sun-umn/Deep-Random-Projector/1_Denoising/models/downsampler.py
code served (permissive licence) · get_code("7aa5f3eab66d010a")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 2, dtype family float, shape (5, 5) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

ARGS = {
    'factor': 2,
    'kernel_type': 'lanczos',
    'phase': 0.0,
    'kernel_width': 5,
    'support': 2,
    'sigma': None,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (5, 5) — shape (5, 5) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_block Not yet run
unverified (harvested, no recorded run)
sun-umn/Deep-Random-Projector/1_Denoising/models/resnet.py
code served (permissive licence) · get_code("357923e66448e342")
How it ran

no invocation recorded.

get_texture_nets Not yet run
unverified (harvested, no recorded run)
sun-umn/Deep-Random-Projector/1_Denoising/models/texture_nets.py
code served (permissive licence) · get_code("4d472667e76c667d")
How it ran

no invocation recorded.

skip Not yet run
unverified (harvested, no recorded run)
sun-umn/Deep-Random-Projector/1_Denoising/models/skip.py
code served (permissive licence) · get_code("c0e07869abc20153")
How it ran

no invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 6 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 0 the same month, 4 later) and 4 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
bn 8 other papers
3 dated earlier, 4 later, 1 same year, order not determinable
1711.10925 (2017-11)
Deep Image Prior
1901.11365 (2019-01)
Noise2Self: Blind Denoising by Self-Supervision
Zang_IntraTomo_Self-Supervised_Learning-Based_Tomography_via_Sinogram_Synthesis_and_Prediction_ICCV_2021_paper (2021 (year only))
IntraTomo: Self-supervised Learning-based Tomography via Sinogram Synthesis and Prediction
and 5 more not named here
act 6 other papers
3 dated earlier, 3 later
1711.10925 (2017-11)
Deep Image Prior
1901.11365 (2019-01)
Noise2Self: Blind Denoising by Self-Supervision
Zang_IntraTomo_Self-Supervised_Learning-Based_Tomography_via_Sinogram_Synthesis_and_Prediction_ICCV_2021_paper (2021 (year only))
IntraTomo: Self-supervised Learning-based Tomography via Sinogram Synthesis and Prediction
and 3 more not named here
conv 6 other papers
3 dated earlier, 2 later, 1 same year, order not determinable
1711.10925 (2017-11)
Deep Image Prior
1901.11365 (2019-01)
Noise2Self: Blind Denoising by Self-Supervision
and 3 more not named here
get_kernel 5 other papers
2 dated earlier, 2 later, 1 same year, order not determinable
2003.13659 (2020-03)
Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation
Zang_IntraTomo_Self-Supervised_Learning-Based_Tomography_via_Sinogram_Synthesis_and_Prediction_ICCV_2021_paper (2021 (year only))
IntraTomo: Self-supervised Learning-based Tomography via Sinogram Synthesis and Prediction
and 2 more not named here
calcualte_PSNR 1 other paper
1 dated earlier
2110.12271 (2021-10)
Self-Validation: Early Stopping for Single-Instance Deep Generative Priors
skip 1 other paper
1 dated earlier
Zang_IntraTomo_Self-Supervised_Learning-Based_Tomography_via_Sinogram_Synthesis_and_Prediction_ICCV_2021_paper (2021 (year only))
IntraTomo: Self-supervised Learning-based Tomography via Sinogram Synthesis and Prediction

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Deep image prior (DIP) has shown great promise in tackling a variety of image restoration (IR) and general visual inverse problems, needing no training data. However, the resulting optimization process is often very slow, inevitably hindering DIP's practical usage for time-sensitive scenarios. In this paper, we focus on IR, and propose two crucial modifications to DIP that help achieve substantial speedup: 1) optimizing the DIP seed while freezing randomly-initialized network weights, and 2) reducing the network depth. In addition, we reintroduce explicit priors, such as sparse gradient prior-encoded by total-variation regularization, to preserve the DIP peak performance. We evaluate the proposed method on three IR tasks, including image denoising, image super-resolution, and image inpainting, against the original DIP and variants, as well as the competing metaDIP that uses metalearning to learn good initializers with extra data. Our method is a clear winner in obtaining competitive restoration quality in a minimal amount of time. Our code is available at https://github.com/sun-umn/Deep-Random-Projector.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("Li_Deep_Random_Projector_Accelerated_Deep_Image_Prior_CVPR_2023_paper")
get_code_for_paper("Li_Deep_Random_Projector_Accelerated_Deep_Image_Prior_CVPR_2023_paper")
have("Li_Deep_Random_Projector_Accelerated_Deep_Image_Prior_CVPR_2023_paper")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/Li_Deep_Random_Projector_Accelerated_Deep_Image_Prior_CVPR_2023_paper.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/Li_Deep_Random_Projector_Accelerated_Deep_Image_Prior_CVPR_2023_paper.svg)](https://syntology.ai/paper/Li_Deep_Random_Projector_Accelerated_Deep_Image_Prior_CVPR_2023_paper)

Connect an agent — have() is free.